How to Use the Braze MCP in Pydantic AI

Q: Can Pydantic AI handle errors when a Braze canvas fails to trigger?

Yes, if triggercanvas fails or returns unexpected data, Pydantic AI catches the error immediately. This allows your application to handle the failure gracefully without corrupting state.

Q: How do I set up the Braze MCP Server with Pydantic AI?

You initialize the connection using the MCPToolset class pointing to your Vinkius HTTP endpoint. Then, pass this toolset directly to your Pydantic AI Agent constructor to expose all ten tools.

Build type-safe Braze integrations with Pydantic AI to validate user updates and campaign triggers at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Braze MCP to Pydantic AI

Create your Vinkius account to connect Braze to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Braze with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe user tracking using Pydantic AI

The `track_user` tool records custom attributes and events, and `identify_user` links user aliases to permanent external IDs. When you connect this Braze MCP Server to Pydantic AI, every attribute update is validated against strict Python types before it gets sent to the API. If your model tries to send a string where a boolean is expected, Pydantic AI raises a validation error immediately. This prevents bad data from corrupting your marketing database, ensuring your user profiles remain clean.

Validate campaign triggers with this MCP Server

The `trigger_campaign` tool fires API-triggered messages, and `trigger_canvas` starts a user journey. Using these tools within Pydantic AI ensures that campaign IDs and trigger properties match your defined data models perfectly. This strict runtime validation means your agent won't execute a broken trigger call. If the LLM generates a malformed payload, the framework catches the validation mismatch before the API call is made, protecting your users from broken messages.

Fetch structured campaign data in Pydantic AI

The `get_campaign_details` tool returns deep metadata for a specific campaign, while `list_campaigns` lists all available campaigns in your workspace. Pydantic AI parses these JSON payloads into typed models, making campaign states predictable for your code through the MCP Server. Instead of dealing with untyped dictionaries, your agent works with validated objects. If the API schema changes, Pydantic AI fails loudly in your test environment, alerting you to the change before it impacts your production workflows.

Setup guide

Set up Braze MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "braze-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Braze tools.",
)

result = await agent.run("List recent Braze transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Braze. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Braze now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Braze MCP in Pydantic AI

The framework uses Pydantic models to validate the parameters for tools like `track_user` at runtime. If the model attempts to send invalid attributes, the execution halts and throws a validation error.

Yes, if `trigger_canvas` fails or returns unexpected data, Pydantic AI catches the error immediately. This allows your application to handle the failure gracefully without corrupting state.

You initialize the connection using the `MCPToolset` class pointing to your Vinkius HTTP endpoint. Then, pass this toolset directly to your Pydantic AI Agent constructor to expose all ten tools.

Yes, you can control which tools are exposed to your agent. You can configure the toolset to only allow read operations like `list_campaigns` and `get_campaign_details`, blocking write actions entirely.

The server runs in an isolated V8 sandbox on Vinkius, processing user IDs and event attributes entirely in memory. No customer data or tracking payloads are stored on our servers, keeping your customer profiles private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript